© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 86824
    Prev
    Next
    INDEX
    Explanations

    present tense forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    инкÑĥ
    -0.07
    ãģ
    -0.06
    ton
    -0.06
    ÎIJ
    -0.06
    tre
    -0.06
    vinc
    -0.06
    Ñĥж
    -0.06
    ool
    -0.06
    evin
    -0.06
    ved
    -0.06
    POSITIVE LOGITS
    /is
    0.07
    naments
    0.07
    /stdc
    0.06
    -invalid
    0.06
    cket
    0.06
    ithe
    0.06
    ackson
    0.06
    >Nama
    0.06
    cribed
    0.06
    ote
    0.06
    Activations Density 0.009%

    No Known Activations